Multiclass Classification Using TensorFlow

In the previous article, I discussed building a linear regression model using Tensorflow. In this article, I will try to solve a multiclass classification problem using Tensorflow. I have used the MNIST-digit recognizer dataset here. Please note that even though a Convolutional Neural Network might have worked better for this problem as this is an image recognition problem, but I have used a generic neural network as I wanted to showcase solving a classification problem using Neural Networks. The dataset consists of 784 pixel columns, where each row represents a 28 x 28 image flattened out into a row vector, and a label column, with the image labels given by the digits the image represent, from 0–9.